MiniMax: MiniMax M2.1

MiniMaxOpen weights

MiniMax: MiniMax M2.1 by MiniMax costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, with a 205K-token context window.

Pricing

Input (per 1M tokens)

$0.30

Output (per 1M tokens)

$1.20

Cached input (per 1M)

$0.03

Provider	Input / 1M	Output / 1M
openrouter	$0.30	$1.20
MiniMax (minimax.io)	$0.30	$1.20

Specifications

Provider: MiniMax
Context window: 205K tokens
Parameters: 229B
Released: Dec 2025
Open weights: Yes
Frontier model: No
Hugging Face: MiniMaxAI/MiniMax-M2.1

Speed & latency

Time to first token

0.45s

Output speed

129 tok/s

Fastest host: bedrock (via vercel-ai-gateway).

Compare MiniMax: MiniMax M2.1 with…

MiniMax: MiniMax M2.1 vs MiniMax M2.7$1.20/1M MiniMax: MiniMax M2.1 vs MiniMax M3$1.20/1M MiniMax: MiniMax M2.1 vs GPT-5.6 Luna$1.20/1M MiniMax: MiniMax M2.1 vs Qwen3 Next 80B A3B Thinking$1.20/1M MiniMax: MiniMax M2.1 vs Inkling Small$1.20/1M MiniMax: MiniMax M2.1 vs KAT-Coder-Pro V1$1.20/1M

FAQ

How much does MiniMax: MiniMax M2.1 cost?

MiniMax: MiniMax M2.1 is priced at $0.30 per 1M input tokens and $1.20 per 1M output tokens. Output tokens cost more than input.

What is MiniMax: MiniMax M2.1's context window?

MiniMax: MiniMax M2.1 supports a context window of 205K tokens — the maximum prompt plus response length it can handle in a single request.

Is MiniMax: MiniMax M2.1 open weight?

Yes — MiniMax: MiniMax M2.1 has openly available weights.

Data as of 2026-10-20. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.